metaharness
Reduces time-to-deployment for custom AI agents by providing pre-built infrastructure (CLI, MCP server, memory, release signing), enabling teams to focus on …
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
- Generate a custom CLI tool with your company branding and Claude integration built-in.
- Set up an MCP server that learns from past interactions and improves over time automatically.
- Create a sandboxed agent environment for testing AI code changes before production deployment.
Reduces time-to-deployment for custom AI agents by providing pre-built infrastructure (CLI, MCP server, memory, release signing), enabling teams to focus on agent logic rather than scaffolding and operational concerns.
Engineering teams building internal AI agents or automation tools needing standardized CLI interfaces and production-grade release management.
https://github.com/ruvnet/metaharness
By ruvnet
How to Get It
npx metaharness
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me generate a custom CLI tool with my company branding and Claude integration built-in
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Simple Meta-Harness on Islo.dev — Hacker News · 51 pts
- Polygraph: A Meta-Harness for Maximum Agent Autonomy — Hacker News · 47 pts
- Omnigent: A Meta-Harness to Combine, Control and Share Your Agents — Hacker News · 15 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 344 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 344 GitHub stars; contributors unknown; last commit 0d ago; license MIT.